Agent swarms and the new model economics · Cursor
We compared old and new agent swarms building SQLite from scratch and found that better coordination delivers similar quality at a fraction of the cost.
Blog / research Earlier this year, we ran experiments to test the limits of scaling agents to cooperate toward a goal. Our hypothesis was that this would unlock a new tier of task scale and complexity. The flagship project was a long-running swarm building a web browser from scratch . It succeeded as a proof of concept, but fell far short of polished software. That work was deliberately empirical. We started from a blank canvas and hill-climbed toward a stable, effective system . Since then, our goal has been to understand the agent swarm well enough to engineer it deliberately. To test that p
saved by
related reading
- Towards self-driving codebases · Cursorcursor.com
- Notes on the Software Factorybenedict.dev
- Scaling long-running autonomous coding · Cursorcursor.com
- Training an Agentic Router for Optimal Cost-Performance on SWE Tasks | Applied Computeappliedcompute.com
- Senior SWE-Benchsenior-swe-bench.snorkel.ai
- Composer2.pdfcursor.com
- Code was our medium for thoughtwattenberger.com
- Patterns and problems in multiagent systemsanthropic.com
- Kimi Agent Swarm: 100 Sub-Agents at Scalekimi.com
- AddyOsmani.com - Long-running Agentsaddyosmani.com
- Shipping at Inference-Speed | Peter Steinbergersteipete.me
- Don’t Build Multi-Agents | Cognitioncognition.ai